Prompt @engineerrprompt
Creator of localGPT | Building something cool! Generative AI, Tech, Arts, Life! youtube.com/@engineerprompt Joined July 2023-
Tweets229
-
Followers758
-
Following548
-
Likes240
If you are looking for end-to-end prototyping with llama3, make sure to checkout this session where I joined the amazing team @AIMakerspace to talk about dataset preparation, model fine-tuning and deployment. Really enjoyed the session. Session: youtube.com/watch?v=anIBtQ…
SLMs like Phi-3-mini are great for small specific tasks but are also great candidates for fine-tuning on your own datasets. Thanks to @UnslothAI, fine-tuning Phi-3-mini is really easy. Learn how to get started here: youtu.be/U5jU4YJodJo
Llama-3 8B with 1M Context. Can anyone run the benchmarks on it?
Llama-3 8B with 1M Context. Can anyone run the benchmarks on it?
Phi-3-mini is a great model for its size but how good is it at RAG, query routing and agentic use? I put it to test in this video: youtu.be/_4hFNzY1iMA
Want to build an AI powered application but don't know where to start? Checkout this session. We will cover dataset creation, finetuning, and deployment of the model so the rest of the world can interact with your creation.
Want to build an AI powered application but don't know where to start? Checkout this session. We will cover dataset creation, finetuning, and deployment of the model so the rest of the world can interact with your creation.
Llama3 out of the box is more compliant with prompts compared to its predecessors. In this video I wanted to explore how uncensored the model is. Testing it via @GroqInc, @Meta and @perplexity_ai youtu.be/9oYGb6t-ybw
Groq API is the fastest inference speed on the market. The fabulous tutorial by @engineerrprompt explains how to get started with LLAMA-3 using the Groq API in your own applications. hubs.la/Q02tRZb40
LLAMA3 from @AIatMeta on @GroqInc is insanely fast. 800 tokens/sec on 8B and ~300 tokens/sec for 70B. Best part, you can use their API for free. Here is how to get started youtu.be/ySwJT3Z1MFI
AI stocks are the new meme stocks......
AI stocks are the new meme stocks......
What's better than LLAMA3? Your own finetuned LLAMA3. Learn how to get started with finetuning using @UnslothAI (one of the best options if you are GPU poor like me :) ) youtu.be/aQmoog_s8HE
First look at llama3, really impressive beyond the benchmarks, the only thing I was hoping was more than 8k context and that 400B version looks on part with Claude Opus youtu.be/b2MPvE1OyHg
We got LLAMA-3!!!!
That was quick! The instruct version of Mixtral 8x22B from @MistralAI looks amazing.
That was quick! The instruct version of Mixtral 8x22B from @MistralAI looks amazing.
I tested the new Mixtral MoE from @MistralAI. For a base model, it's really impressive. Here is the video: youtu.be/VwbBBcvsWZM
If you are building RAG pipelines, you need to checkout ColBERTv2 (by @lateinteraction) as possible replacement to Dense Embeddings. RAGatouille by @bclavie is the easiest way to get started. Learn how to use it in @LangChainAI and @llama_index youtu.be/kEgeegk9iqo
OpenAI is finally open 😅
IAComunIA @IAcomunIA
420 Followers 2K Following Descubre todo el poder de la IA a tu alcance con ✨IAcomunIA 🤖 IA Explorador 💬 Comparto IA 👉 Comparo IA ✨Explora las posibilidades ✨ https://t.co/8ITq0xaBiL
Dania Chaudet @ChaudetChaud
54 Followers 5K Following
Frankie Becker @BeckerFran98877
13 Followers 813 Following
GemmaDavy @tVk39uzM4mM20L
5 Followers 298 Following
vishnu k @vishnuk15649289
0 Followers 12 Following
Jule Pam @PamJule29202
78 Followers 5K Following
VirginiaMorton @eX828DmL075d5g
11 Followers 425 Following
Ayan @Ayan_sh003
13 Followers 133 Following Full Stack Developer 🚀 | Gopher| MERN Stack Explorer 💻 | Lifelong Learner 📚 #CodeLife #TechJourney
Raj Kumar @rajkstats
85 Followers 1K Following Analytics-eng @kooindia, Statistician, opinions are my own, writing at https://t.co/Y4EaapfHcA
Federico Galassi @federicogalassi
511 Followers 377 Following Software craftsman. Googler. I love javascript, ruby, vim, git, the pomodoro technique, agile and books.
Pamela Randolph @PamelaRand8462
122 Followers 3K Following
Francesco Mugnai @francescomugnai
6K Followers 3K Following Full stack developer and full-time father. Currently obsessed with AI 😁
Priyam kakati @Priyamkakati46
31 Followers 760 Following Full stack data scientist @kornferry|| Equity investor || MLops || 14K+ LinkedIn 📈 || Follow me on linkedin! 👇🏼
Virgie Cieri @CieriVirgi
80 Followers 5K Following
Michael Leo @Michael31887303
67 Followers 532 Following Msc in International banking(UK) scientific geek，an amateur in hacker,Quantum, AI, Blockchain & Biotech , competence in：C/C++,CUDA,3D printing, FreeCAD，ESP32
Marcin Mroczek @MarcinMroczek1
132 Followers 560 Following
Han S. Kim @REALMONEYHK
9 Followers 47 Following Chief tech lead and researcher at CLARUS Money Project.
Dissenting Data @DissentingData
0 Followers 5 Following I never know what to put here. Tech Enthusiast. Data Wonk (Real Estate and Financial data domains). I can get a little OCD with Open Source LLM models and AI
Arline Schuchard @ArlineSchu37079
77 Followers 5K Following
Fenil @fenil
256 Followers 575 Following
FNG @x_nog
20 Followers 176 Following
Hien Nguyen @semtechvn
32 Followers 374 Following Associate Professor of Computer Science, AI Educator.
大良造 @wolfofyunmeng
48 Followers 1K Following
Andrew Turner @turn61547
46 Followers 336 Following An Intelligence attempting to self-improve. Likes don’t mean anything. Replies don’t mean anything. YMMV.
Siddhesh Rane @siddheshrane24
210 Followers 992 Following Maker. Thinker. Sr. Software Engineer @SAP. Currently, building E-Com SaaS. Interested in AI, Crypto, Startups & Stock markets.
Jorge GX @JorgeGarciaX
200 Followers 2K Following Cloud Solution Engineer for Data Applications & Belgian K8s Meetup coorganisor
Shafaq⚡️AI Infras.. @shafaq110
265 Followers 2K Following Local Clean Delivery @shoponomik, LaunchPad Seed Fund @elementalexcel, @parkonomik AI, mobile personalization @insnap_inc (acq.) @Honest, Analytics @GREE_corp
Jack Reacher @JackReach516
76 Followers 1K Following
Garry Golden @garrygolden
6K Followers 6K Following Futurist w/ real clients. Founder - Creative Learning Space: https://t.co/xwzOBruoN0 Here: Hydrogen, Cardano+Ergo, Space + Parenting + https://t.co/n9ckXtjRK2
Cheng Yang @yangcheng
297 Followers 2K Following co-founder https://t.co/O4DxnTK18e ex Scale AWS Uber LinkedIn
Bem vindos ao Evanjeg.. @ZeRuelabr
51 Followers 644 Following
siva kumar @sivakum38269090
2 Followers 83 Following
Weyland @weymarjohansson
461 Followers 2K Following the antics of this fly alarm me: can an eagle tell a lie?
John Sharpe 🏴 @JohnSharpe8020
295 Followers 541 Following 🏴Automation, 🏴AI, 🏴Data, 🏴Star & 80/20 Principle, 🏴 Equipment, 🏴Tools, and 🏴Leverage
Tobias @Caruso33
274 Followers 3K Following Co-Founder https://t.co/gTdd7Oc6W3, Web3 Eng. https://t.co/6t1dKAOaHj
Dan @DRMTechGG
82 Followers 579 Following PHP, Laravel, Javascript, Vue.js, Go, Rust, C, C++ | Valorant, Apex Legends | Streams at https://t.co/6qNDF2PPS1 | @teachkimi ❤ | 🇵🇭🇯🇵
AI Makerspace @AIMakerspace
645 Followers 5 Following The world's leading community for people who want to build production LLM applications. Build 🏗️ Ship 🚢 Share 🚀 🧑💻 https://t.co/DnEWIh5kfH
Daniel San @dani_avila7
5K Followers 1K Following Building artificial intelligence tools 🤖 https://t.co/PxOrsWzI55
Paul from Dentro @dentro__ai
71 Followers 94 Following AI-as-a-service for your middle sized business 🤝 Building kick-ass AI apps faster than you can say 'ChatGPT'. Ex @BrokkrFinance
Wing Lian (caseus) @winglian
9K Followers 2K Following @axolotl_ai OSS maintainer. Axolotl AI founder. AI/ML tinkerer. Building tools for everyone. ☕ https://t.co/3ni1V4rI9w
Tereza Tizkova @tereza_tizkova
3K Followers 1K Following Founding DevRel @e2b_dev | Mathematics Grad. | I like cheese
Maziyar PANAHI @MaziyarPanahi
2K Followers 471 Following Principal AI/ML/Data Engineer @CNRS @ISCPIF | Spark NLP Lead | https://t.co/6r6GnF0GiY ❤️ #opensource
Mike Schroepfer @schrep
104K Followers 280 Following Partner @Gigascale, Sr Fellow (Formerly CTO) @Meta, founder @AdditionalVent, . Investing in tech and science to fight climate change. AI
E2B @e2b_dev
4K Followers 4 Following Open-source code interpreting SDK for AI apps | Hiring! 👉 https://t.co/WTLBOEvNRx
Mike Lewis @ml_perception
6K Followers 228 Following Llama3 pre-training lead. Partially to blame for things like the Cicero Diplomacy bot, BART, RoBERTa, kNN-LM, top-k sampling & Deal Or No Deal.
comma @comma_ai
83K Followers 37 Following openpilot can drive for hours without driver action and works on 250+ cars like Hyundai & Toyota. See if your car is compatible at https://t.co/YQYNZrCxan
Yohei @yoheinakajima
71K Followers 8K Following VC by day, builder by night: @untappedvc, @babyagi_, @pixelbeastsnft. Build-in-public log: https://t.co/UdHHGbZba5
Maria Khalusova @mariaKhalusova
5K Followers 726 Following Always growing. LLM whisperer, RAG tinkerer, tech generalist, educator. She/her. 🥑 at @UnstructuredIO, previously @huggingface, @DVCorg, @JetBrains
Edward @aestheticedwar1
838 Followers 382 Following Machine Learning Engineer at @weaviate_io passionate about open source, machine learning and indie games! ✨
A.I.Warper @AIWarper
12K Followers 126 Following Sharing my creative AI experiments • Business Inquiries (consulting ONLY - no commission at this time): [email protected]
Zach Mueller @TheZachMueller
10K Followers 396 Following 🤗 Technical Lead for the Accelerate Project | Passionate about Open Source | Nerd who enjoys touching the grass | #ADHD | He/Him
Martin Shkreli (e/acc.. @MartinShkreli
170K Followers 4K Following https://t.co/muasIr0PuD [email protected] https://t.co/GUy99qMi2O - join our Discord!
Yoshiki Miura @miiura
4K Followers 818 Following AI Product Engineer and Founder of Morphic Morphic: A fully open-source AI-powered answer engine with a generative UI BabyAGI UI: An open-source UI for BabyAGI
Josh Tobin @josh_tobin_
11K Followers 1K Following ML-powered products @gantry_ml @full_stack_dl. Previously @Berkeley_EECS PhD and @openai
Eugene Yan @eugeneyan
17K Followers 602 Following ML, Recsys, LLMs @ Amazon. Prev: Alibaba, Lazada, IBM, startup. Building ML systems to serve customers at scale; Writing to learn & teach.
AI Coffee Break with .. @AICoffeeBreak
7K Followers 391 Following 📺 ML Youtuber https://t.co/ZDot8670KO 👩🎓 PhD student in Computational Linguistics @ Heidelberg University | Impressum: https://t.co/sKu3Rh0sQ4
Lewis Tunstall @_lewtun
9K Followers 425 Following 🤗 LLM engineering & research @huggingface 📖 Co-author of "NLP with Transformers" book 💥 Ex-particle physicist 🤘 Occasional guitarist 🇦🇺 in 🇨🇭
Lysandre @LysandreJik
7K Followers 582 Following Head of Open-Source at Hugging Face. Maintainer of 🤗/Transformers. I tweet about Open Source. He/him
Sergios Karagiannakos @KarSergios
2K Followers 1K Following Creator of AI Summer @theaisummer | Data Engineer at @CausalyAI | 📖 Author of Deep Learning in Production (https://t.co/rzZd8VeBQH)
Aakash Kumar Nain @A_K_Nain
9K Followers 673 Following Sr. ML Engineer | Keras 3 Collaborator | @GoogleDevExpert in Machine Learning | @TensorFlow addons maintainer l ML is all I do | Views are my own!
Tim Scarfe @ecsquendor
7K Followers 1K Following CTO @XRAIGlass. Ex-Principal ML engineer @Microsoft. Ph.D in machine learning. CEO @MLStreetTalk pod
Goku Mohandas @GokuMohandas
14K Followers 116 Following ML @anyscalecompute + @raydistributed ← 🌏 Founder @MadeWithML (acq) ← ⚕️ ML Lead @Ciitizen (acq) ← 🍎 ML Engineer @Apple ← 🧬 Bio + ChemE @JohnsHopkins
Framer @framer
137K Followers 365 Following The internet is your canvas. Design and publish stunning sites. Start for free.
Sam Whitmore @sjwhitmore
12K Followers 2K Following building @newcomputer. not a cat (or a man) in real life. I like to run a lot! @kensho @harvard @StuyNY
Erik Schluntz @ErikSchluntz
2K Followers 238 Following Member of Technical Staff at Anthropic Co-founder at @CobaltRobotics Co-founder at Posmetrics (acquired) GoogleX, @SpaceX, @Harvard EE '15, Forbes 30u30 '18
ifioravanti @ivanfioravanti
5K Followers 1K Following Co-founder and CTO of @CoreViewHQ GenAI/LLM addicted, Apple MLX, Ollama, Microsoft 365, Azure, Kubernetes, Investor in innovation
1517 Fund @1517fund
13K Followers 339 Following We back dropouts, renegade students, and deep tech scientists at the earliest stages, before anybody else. Want to chat? Reach out:👇
Chapter One @chapterone
21K Followers 105 Following Chapter One is an early-stage fund. We are seeking protagonists - those who are eager to embark on the formidable task of inching the world forward.
Sara Du @saraduit
34K Followers 893 Following ceo & cofounder @alloyautomation | prev @harvard @ycombinator
sarah guo // convicti.. @saranormous
91K Followers 3K Following startup investor and builder, founder @w_conviction. accelerating AI adoption, interested in progress. tech podcast: @nopriorspod
Giannis @giannis2two
197 Followers 112 Following Member of Technical Staff at @cohere, CS + Math @MIT, primarily european but surprisingly american
Eren Bali @erenbali
55K Followers 2K Following Human founder of @carbonhealth and @udemy (NASDAQ $UDMY)
Sholto Douglas @_sholtodouglas
15K Followers 861 Following Scaling Gemini @Deepmind - working towards intelligence too cheap to meter
Pliny the Prompter �.. @elder_plinius
13K Followers 1K Following latent space liberator, breaker of markov chains, 1337 ai red teamer, white hat, architect-healer, cogsci 🐻
SambaNova Systems @SambaNovaAI
4K Followers 717 Following We bring #AI innovations developed in advanced research to organizations around the world. Sign up for updates to stay ahead of AI: https://t.co/bGeeh5JSt0
AI21 Labs @AI21Labs
6K Followers 90 Following AI21 Labs builds Foundation Models and AI Systems for the enterprise that accelerate the use of GenAI in production. 🥂Meet Jamba https://t.co/xUBjKZHKVH
A.M. @AMplayslife
2K Followers 89 Following Learning 12 skills in 12 months in order to make $10k/m. With the goal of becoming an Expert in each Skill | Follow Along to Learn and See My Journey
Erik Meijer @headinthebox
27K Followers 0 Following
Sami Hamdi سامي �.. @SALHACHIMI
82K Followers 2K Following MD @Theiinterest. Publicly a commentator on MENA while privately advising companies/stakeholders. إعلامي @AlMustakillah1 Enquiries: [email protected]
Chief AI Officer @chiefaioffice
20K Followers 633 Following Writing a daily report on VC activity in AI for 5000+ investors, founders → https://t.co/guDR0d4IA7 // By @IamTalin
AI Notkilleveryoneism.. @AISafetyMemes
33K Followers 825 Following Techno-optimist, but AGI is not like the other technologies. Step 1: make memes. Step 2: ??? Step 3: lower p(doom)
its true. we are working on it :)
“I don’t give a shit about AGI. I want this technology to deliver on the promise it has made. And it has not.” —Nick Frosst, @cohere co-founder
A Whisper transcribing which takes just 326ms for a 60s audio clip! 🤯 Pair this with @GroqInc, and you'll have an assistant that finishes tasks faster than you can explain yourself in the next 60 seconds! Definitely check this out!
BOOM! Whisper + Speaker Diarisation! 🔥 Blazingly fast meeting transcription all with a simple call to an API - powered by Inference Endpoints ⚡ - Whisper to transcribe speech to text (w/ Flash Attention) - Diarization to break down the transcription by speakers (w/ Pyannote)…
ColBERT for the win! Great to see evaluations like this, super easy to represent ColBERT in @vespaengine "Our best performing method for handling RAG Retrieval on all datasets was ColBERT v2 with SentenceSplitter chunking." superlinked.com/vectorhub/arti…
PSA to not believe every AI thing you read online! My “100 quadrillion” parameters pic is spreading around the internet 🛜 Most of big AI news accounts have no idea what they are talking about
Billionaire Michael Bloomberg once boasted that the NYPD was his private army. Tonight, it’s the NetanYahu PD – dedicated to stamping out a righteous student protest against the worst war criminal of this century and his genocidal regime.
Police have broken into Hamilton Hall at Columbia University to arrest students inside who’ve taken it over last night in order to pressure the university to divest
AutoTrain isn't just about LLM finetuning. 8 Tasks supported excluding 5 different types of LLM finetuning 💥
dolphin-2.9-mixtral-8x22b is released! Compute sponsored by @CrusoeEnergy Trained by myself, @LucasAtkins7, @FernandoNetoAi FFT using Laser Scanner to selectively target 50% of the layers. Uncensored models obey! You are responsible for anything you generate with it.
Phi-3 notebook out! Finetune Phi 2x faster and use 50% less VRAM than HF+FA2 with @UnslothAI! Had to Mistral-fy it due to sliding window attention, & fixed the 2048/2047 SWA bug. Also unfused Attention & MLP, so some diff in QLoRA loss but 16bit the same. colab.research.google.com/drive/1NvkBmkH…
New ORPO Colab for Llama-3 8b is out! ORPO combines SFT & DPO into 1 step, so no more 2 step approach! Plus with @UnslothAI, finetuning is 2x faster, uses 80% less VRAM & 4x longer contexts are possible! Thanks to oKatanaaa & At&Dev for making this work! colab.research.google.com/drive/11t4njE3…
I published my filtered and uncensored dataset for Dolphin-2.9 on @huggingface so if you wanna make your own spin on Dolphin, or just see how Dolphin is created, you can check it out. Thanks to all the upstream dataset creators for open source data! huggingface.co/datasets/cogni…
Unsloth has surpassed 500K+ monthly model downloads on @huggingface! 🥳 🦥 Thanks for the support! 🩷 See our collection of 4bit models + more: huggingface.co/unsloth
New 🤖 agents video out using LangGraph (@LangChainAI) powered by Llama3 70B on @GroqInc to make an Email Agent youtu.be/lvQ96Ssesfk
A reminder that no one knows what they're doing in deep learning and why things work and that the best we can do is pray for our models to perform 🤣
Mozilla published a nice writeup on how llamafile helped them evaluate the quality of AI models and quantization formats. The writeup goes into detail on the code, costs, and has a heartwarming story on some history with the local LLaMA community. blog.mozilla.ai/local-llm-as-j…
It's been a week since LLaMA 3 dropped. In that time, we've: - extended context from 8K -> 128K - trained multiple ridiculously performant fine-tunes - got inference working at 800+ tokens/second If Meta keeps releasing OSS models, closed providers won't be able to compete.
Love this, just came up IRL and often true
🦙 Have you fine-tuned Llama 3 and built an end-to-end prototype yet? Come May 1 to see the entire end-to-end process with @huggingface tools! Our friend @engineerrprompt will join us for the walkthrough and Q&A! lu.ma/llmappshf
@winglian @Orwelian84 You can set RoPE config values under Advanced Configuration > Model Initialization:
Trends for United States
You might like
